RC-Mixup: A Data Augmentation Strategy against Noisy Data for Regression Tasks

TL;DR

RC-Mixup is a novel data augmentation strategy that combines C-Mixup with multi-round robust training to improve regression model performance on noisy data, leveraging a synergistic, data-centric approach.

Contribution

The paper introduces RC-Mixup, a new data augmentation method that enhances robust training for regression tasks with noisy data by integrating C-Mixup with multi-round training without modifying existing algorithms.

Findings

RC-Mixup significantly outperforms C-Mixup and robust training baselines.

RC-Mixup can be integrated with various robust training methods.

RC-Mixup improves data quality for better regression performance.

Abstract

We study the problem of robust data augmentation for regression tasks in the presence of noisy data. Data augmentation is essential for generalizing deep learning models, but most of the techniques like the popular Mixup are primarily designed for classification tasks on image data. Recently, there are also Mixup techniques that are specialized to regression tasks like C-Mixup. In comparison to Mixup, which takes linear interpolations of pairs of samples, C-Mixup is more selective in which samples to mix based on their label distances for better regression performance. However, C-Mixup does not distinguish noisy versus clean samples, which can be problematic when mixing and lead to suboptimal model performance. At the same time, robust training has been heavily studied where the goal is to train accurate models against noisy data through multiple rounds of model training. We thus propose our data augmentation strategy RC-Mixup, which tightly integrates C-Mixup with multi-round robust training methods for a synergistic effect. In particular, C-Mixup improves robust training in identifying clean data, while robust training provides cleaner data to C-Mixup for it to perform better. A key advantage of RC-Mixup is that it is data-centric where the robust model training algorithm itself does not need to be modified, but can simply benefit from data mixing. We show in our experiments that RC-Mixup significantly outperforms C-Mixup and robust training baselines on noisy data benchmarks and can be integrated with various robust training methods.